Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Old Man Tiber

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bevel
    0.31
    拡
    0.31
    omod
    0.30
     ολο
    0.29
    >();
    0.28
    utenção
    0.28
    0.27
     prv
    0.27
    absor
    0.27
    orrh
    0.26
    POSITIVE LOGITS
     Gandhi
    0.38
     Putin
    0.37
     Sartre
    0.37
     Netanyahu
    0.36
     Spielberg
    0.35
     Nietzsche
    0.34
     Luffy
    0.34
     Zuckerberg
    0.32
     Erdoğan
    0.32
     Hitler
    0.32
    Act Density 0.014%

    No Known Activations